Around 1989, Steven Schueler started working on a computer program that could perform symptom triage. The intent was to create something that patients could use to safely decide what to do when they were sick. In 1990, his company DSHI Systems released “Home Medical Advisor” on a floppy disk. Later it was issued on CD-ROM’s, and claims to have sold over 2 million copies over the years. A major win for DSHI since 1999 has been its adoption by the Veterans Health Administration (VHA) as the Veterans Health Gateway (VHG). VHG provides over 300 symptom/condition-based triage algorithms and related patient education information and is used by VHA nurses to provide health advice via the telephone.

FreeMD is the free online version of the same underlying triage application. It  uses video to conduct the interview, ask questions and then generates a custom web page that contains care instructions and suggested next steps. I tested it with a few hypothetical cases (from benign nose bleed to serious UTI) and it seemed to do fine for basic diagnosis. With vague complaints like diffuse abdominal pain and vomiting, it stayed roughly in the right categories at a high-level (appendicitis, pancreatitis, kidney stones, gallbladder disease, intestinal obstruction).

Is the underlying logic based on hierarchical structured programming or a more sophisticated expert system with forward and backward chaining algorithms? I don’t know. My interest in FreeMD spiked when I saw the 100K+ unique visitors/month statistic. They are consistently generating a lot of traffic, so there’s got to be fairly comprehensive content and at least some utility in the service. My personal impression is that as a patient-oriented triage tool, it does well. Of course, provider-oriented decision support is tougher and I don’t expect it to hold up like Mcyin or DXplain.

I’m also intrigued why DSHI systems chose to make their application available for free, when the revenue model seems to be based on licensing/co-branding with partners. I was half-expecting to see a feedback loop on FreeMD (like “Was this the right diagnosis? Let us know”) since one of the major reasons for open-sourcing anything is to leverage wisdom of crowds. But there isn’t anything like that, so maybe its all about gaining awareness and marketing the application.

Update: Connected with Dr. Steven Schueler after writing this post. He correctly identified that FreeMD is a triage system, so its a bit unfair to compare it with diagnostic decision support systems like Mycin/DXplain.

Usually I’m wary of putting time into big-budget health portals, but San Francisco based Healthline deserves a mention. They have a portfolio of healthcare search, navigation and content that is syndicated through a growing network of big web properties like AARP, Health.com, iVillage, AOL etc.

Healthline was founded in 1999 as YourDoctor.com and was re-launched as Healthline Networks in 2005. It’s got some deep-pocket investors behind it (Aetna, NBCU, Kaiser Permanente, Reed Elsevier, US News & World Report to name a few) so I’m not surprised that they have managed to create (what they call as) ‘Consumer Healthcare Taxonomy’ of >1 million terms and 250K medical concepts. That is what powers their proprietary ability to organize and present contextually-relevant health information to a viewer. Personally I dont think much of it, given that there are plenty of precursors in the medical ontology area (SNOMED, UMLS…) that match this feat.

So Healthline can power health search in multiple ways (symptom, treatment, doctor, drug) and help consumers navigate to the right information. They have also branched out into health-specific ad network, PHR etc. Regardless, I’m interested in mentioning Healthline because of their excellent 3D Body Maps. They have a neat library of 3D animations that lets you partially control and understand body structure and function. Much like CareFlash. Development of these consumer-oriented educational health content repositories is a positive trend, although it’d be much nicer if all these individual attempts were cataloged in one place, giving a complete guide to educational 3D health and wellness content on the web. Like what Clicker does for Internet television.

SimulConsult is a diagnostic decision support system started by Dr.Michael Segal. It covers 1,800 diseases that have at least one neurological finding in them.

SimulConsult has an interesting logic behind it. Roughly speaking, its knowledge is derived from a ‘computational wiki’ that is restricted to physician users only. So its database is not only open for viewing, but users can submit modifications to the database. The system performs bayesian pattern matching and also considers temporal information like the age of onset and disappearance of each finding for each disease under consideration.

According to Dr.Segal, there are about 33,000 data points (disease findings) in the system and the future expansion plans are to include more of metabolism and genetic diseases. Interestingly, the wiki approach for knowledge gathering in healthcare is becoming more common (AskDrWiki, WikiDoc, wikiMD to note a few- more on them later).

Feb 20, 2009 Update: Got an email today announcing that those who contribute information to SimulConsult database will now get paid for their contributions. As they are adding sponsored links in the software, I guess it makes sense to share the wealth. More info here.

With a play on google’s name, MEDgle offers symptom based health information search. The idea is to ‘empower patients in their discussions with physicians’, by making relevant content easy to find.

The navigation is pretty simple and straightforward. MEDgle’s output is a probabilistic list of disease/conditions based on the user input. The content is authored by their 3-physician team and is based on publicly available information available such as the Center for Disease Control and National Institutes of Health. Where probability estimates were not available, they have used their own practice experience to fill in the gaps.

The need for a healthcare vertical search engine is widely realized, and like everything else, it opens up the ability for potential (ab)use with self-diagnosing hypochondriacs. Skepticism aside, I did a search using a common symptom (difficulty in walking, heel pain) and found it easy to navigate to a list of links and information around bone spur and plantar fasciitis. The “Related Local Doctors” section for finding local providers relevant for your symptoms is a neat idea too.

There is an obvious limit to the utility of such tools- Alexia Estabrook’s blogpost talks about MEDgle’s performance for a more complex query. Although that points to the Achilles heel of any diagnostic decision support system today; it’s hard to model the entire spectrum of disease-symptom relationship in an all-inclusive, 100% accurate way. It has more to do with the ever-expanding body of medical knowledge than the lack of technical prowess. That why medicine is a science and an art.

PS: You can read the interviews of some of MEDgle team members here and here.